feat: absorb cloudron kuma monitoring from PFVCluster [#727]

monitoring/ = cloudron-apps.txt (55-app inventory, #435) + kuma-cloudron-sync.py (coverage checker, path re-rooted). Removed from PFVCluster in the paired commit there. Meat: https://projects.knownelement.com/issues/727#note-3913
2026-09-02 18:51:04 -05:00
parent 0e67f17112
commit 4806e6f24d
4 changed files with 191 additions and 0 deletions
@@ -0,0 +1,62 @@
+ap4ap.org
+bi.knownelement.com
+booking.rackrental.net
+booking.reachableceo.com
+booking.roguetechnologies.net
+booking.startinglineproductions.com
+booking.teamrental.net
+booking.thepeernet.com
+bookmarks.knownelement.com
+broadcast.thepeernet.com
+broadcast.turnsys.com
+building-management.knownelement.com
+chat.knownelement.com
+community.turnsys.com
+design.knownelement.com
+erp.knownelement.com
+esign.knownelement.com
+ezeda.org
+ezpodstack.org
+finance.turnsys.com
+forms.knownelement.com
+git.knownelement.com
+grafana.knownelement.com
+helpdesk.knownelement.com
+hfnfc.net
+hfnoc.net
+ipam.knownelement.com
+jupyter.knownelement.com
+knownelement.com
+learn.turnsys.com
+marketing.turnsys.com
+matrix.turnsys.com
+meetmorse.com
+merchantsofhope.org
+my.knownelement.com
+nextcloud.knownelement.com
+paperless.knownelement.com
+photos.knownelement.com
+phplist.knownelement.com
+projects.knownelement.com
+pwvault.turnsys.com
+rackrental.net
+reachableceo.com
+readlater.knownelement.com
+recordings.thepeernet.com
+redwfo.com
+rss.knownelement.com
+rwscp.net
+sidedoorgroup.org
+sol-calc.com
+startinglineproductions.com
+staticbits.knownelement.com
+status.knownelement.com
+suborbital-systems.com
+surveys.knownelement.com
+thepeernet.com
+turnsys.com
+uksrs.org
+url.knownelement.com
+webmail.knownelement.com
+webstats.knownelement.com
+whiteboard.knownelement.com
@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+"""kuma-cloudron-sync.py — Uptime Kuma Cloudron app coverage sync [#435]
+
+Compares the committed Cloudron app list (monitoring/cloudron-apps.txt, ex-PFVCluster) against
+live Kuma http monitors, reports coverage gaps, and (with --add) creates the
+missing monitors INSIDE the "Cloud Systems" group (never root — founder
+ruling 2026-09-02: monitors go in groups).
+
+App list provenance: CT-log enumeration + DNS resolve + HTTPS probe across
+all 23 Kuma-monaged domains (2026-09-02, see #435 note). Re-derive with
+/tmp-style probe pipeline or a read-only Cloudron API diff when a token
+lands. Two apps (forms/learn) return 500 today — monitored red on purpose
+(#681).
+
+Env (from ~/.creds/uptime-kuma.env):
+  UPTIME_KUMA_URL, UPTIME_KUMA_TOKEN
+
+Usage:
+  python3 kuma-cloudron-sync.py [--add] [--limit N] [--group-id ID]
+    --add     create missing monitors
+    --limit N add at most N (canary mode)
+    --group-id ID  parent group (default: 48 = "Cloud Systems")
+"""
+import argparse
+import os
+import sys
+import time
+from pathlib import Path
+
+import socketio
+
+HERE = Path(__file__).resolve().parent / "cloudron-apps.txt"
+DEFAULT_GROUP = 277  # "Cloudron" group (founder-directed 2026-09-02)
+
+
+def load_apps():
+    apps = []
+    for line in HERE.read_text().splitlines():
+        line = line.split("#", 1)[0].strip()
+        if line:
+            apps.append(line)
+    return apps
+
+
+def kuma_connect():
+    sio = socketio.Client(reconnection=False)
+    state = {}
+
+    @sio.on("monitorList")
+    def _ml(d):
+        state["ml"] = d
+
+    sio.connect(
+        os.environ["UPTIME_KUMA_URL"], transports=["websocket"], wait_timeout=30
+    )
+    r = sio.call("loginByToken", os.environ["UPTIME_KUMA_TOKEN"], timeout=30)
+    if not (isinstance(r, dict) and r.get("ok")):
+        raise SystemExit(f"login failed: {r}")
+    sio.emit("monitorList")
+    for _ in range(20):
+        if "ml" in state:
+            break
+        time.sleep(1)
+    return sio, state.get("ml", {})
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--add", action="store_true")
+    ap.add_argument("--limit", type=int, default=0)
+    ap.add_argument("--group-id", type=int, default=DEFAULT_GROUP)
+    args = ap.parse_args()
+
+    apps = load_apps()
+    sio, mons = kuma_connect()
+    try:
+        covered = set()
+        for m in mons.values():
+            name = (m.get("name") or "").strip().lower()
+            url = (m.get("url") or "").strip().lower()
+            for fqdn in apps:
+                if fqdn == name or url.rstrip("/") in (
+                    f"https://{fqdn}".rstrip("/"),
+                    f"https://{fqdn}/".rstrip("/"),
+                ):
+                    covered.add(fqdn)
+        missing = [a for a in apps if a not in covered]
+
+        print(f"apps in list: {len(apps)}  covered: {len(covered)}  missing: {len(missing)}")
+        for fqdn in missing:
+            print(f"  MISSING {fqdn}")
+
+        if args.add and missing:
+            batch = missing if not args.limit else missing[: args.limit]
+            for fqdn in batch:
+                payload = {
+                    "type": "http",
+                    "name": fqdn,
+                    "url": f"https://{fqdn}/",
+                    "interval": 60,
+                    "retryInterval": 60,
+                    "resendInterval": 0,
+                    "maxretries": 2,
+                    "notificationIDList": {"1": True, "2": True},
+                    "upsideDown": False,
+                    "description": "Cloudron app HTTP 200 (#435)",
+                    "httpBodyEncoding": "json",
+                    "accepted_statuscodes": ["200-299"],
+                    "conditions": [],
+                    "active": True,
+                    "parent": args.group_id,
+                    "maxredirects": 10,
+                }
+                r = sio.call("add", payload, timeout=30)
+                ok = isinstance(r, dict) and r.get("ok")
+                print(f"  ADD {fqdn}: {'id=' + str(r.get('monitorID')) if ok else r}")
+    finally:
+        sio.disconnect()
+
+
+if __name__ == "__main__":
+    main()